[PATCH] x86/CPUID: add further "fast repeated string ops" feature flags

[PATCH] x86/CPUID: add further "fast repeated string ops" feature flags

[Jan Beulich]

Like ERMS this can always be exposed to guests, but I guess once we
introduce full validation we want to make sure we don't reject incoming
policies with any of these set when in the raw/host policies they're
clear.

Signed-off-by: Jan Beulich <jbeulich@suse.com>

--- a/tools/libs/light/libxl_cpuid.c
+++ b/tools/libs/light/libxl_cpuid.c
@@ -215,6 +215,7 @@ int libxl_cpuid_parse_config(libxl_cpuid
 
         {"avx512-4vnniw",0x00000007,  0, CPUID_REG_EDX,  2,  1},
         {"avx512-4fmaps",0x00000007,  0, CPUID_REG_EDX,  3,  1},
+        {"fsrm",         0x00000007,  0, CPUID_REG_EDX,  4,  1},
         {"avx512-vp2intersect",0x00000007,0,CPUID_REG_EDX,8, 1},
         {"srbds-ctrl",   0x00000007,  0, CPUID_REG_EDX,  9,  1},
         {"md-clear",     0x00000007,  0, CPUID_REG_EDX, 10,  1},
@@ -229,6 +230,9 @@ int libxl_cpuid_parse_config(libxl_cpuid
 
         {"avx-vnni",     0x00000007,  1, CPUID_REG_EAX,  4,  1},
         {"avx512-bf16",  0x00000007,  1, CPUID_REG_EAX,  5,  1},
+        {"fzrm",         0x00000007,  1, CPUID_REG_EAX, 10,  1},
+        {"fsrs",         0x00000007,  1, CPUID_REG_EAX, 11,  1},
+        {"fsrcs",        0x00000007,  1, CPUID_REG_EAX, 12,  1},
 
         {"lahfsahf",     0x80000001, NA, CPUID_REG_ECX,  0,  1},
         {"cmplegacy",    0x80000001, NA, CPUID_REG_ECX,  1,  1},
--- a/tools/misc/xen-cpuid.c
+++ b/tools/misc/xen-cpuid.c
@@ -177,6 +177,9 @@ static const char *const str_7d0[32] =
 static const char *const str_7a1[32] =
 {
     [ 4] = "avx-vnni",      [ 5] = "avx512-bf16",
+
+    [10] = "fzrm",          [11] = "fsrs",
+    [12] = "fsrcs",
 };
 
 static const struct {
--- a/xen/include/public/arch-x86/cpufeatureset.h
+++ b/xen/include/public/arch-x86/cpufeatureset.h
@@ -261,6 +261,7 @@ XEN_CPUFEATURE(SSB_NO,        8*32+26) /
 /* Intel-defined CPU features, CPUID level 0x00000007:0.edx, word 9 */
 XEN_CPUFEATURE(AVX512_4VNNIW, 9*32+ 2) /*A  AVX512 Neural Network Instructions */
 XEN_CPUFEATURE(AVX512_4FMAPS, 9*32+ 3) /*A  AVX512 Multiply Accumulation Single Precision */
+XEN_CPUFEATURE(FSRM,          9*32+ 4) /*A  Fast Short REP MOVS */
 XEN_CPUFEATURE(AVX512_VP2INTERSECT, 9*32+8) /*a  VP2INTERSECT{D,Q} insns */
 XEN_CPUFEATURE(SRBDS_CTRL,    9*32+ 9) /*   MSR_MCU_OPT_CTRL and RNGDS_MITG_DIS. */
 XEN_CPUFEATURE(MD_CLEAR,      9*32+10) /*A  VERW clears microarchitectural buffers */
@@ -277,6 +278,9 @@ XEN_CPUFEATURE(SSBD,          9*32+31) /
 /* Intel-defined CPU features, CPUID level 0x00000007:1.eax, word 10 */
 XEN_CPUFEATURE(AVX_VNNI,     10*32+ 4) /*A  AVX-VNNI Instructions */
 XEN_CPUFEATURE(AVX512_BF16,  10*32+ 5) /*A  AVX512 BFloat16 Instructions */
+XEN_CPUFEATURE(FZRM,         10*32+10) /*A  Fast Zero-length REP MOVSB */
+XEN_CPUFEATURE(FSRS,         10*32+11) /*A  Fast Short REP STOSB */
+XEN_CPUFEATURE(FSRCS,        10*32+12) /*A  Fast Short REP CMPSB/SCASB */
 
 #endif /* XEN_CPUFEATURE */
 

Re: [PATCH] x86/CPUID: add further "fast repeated string ops" feature flags

[Andrew Cooper]

On 16/04/2021 14:22, Jan Beulich wrote:
> Like ERMS this can always be exposed to guests, but I guess once we
> introduce full validation we want to make sure we don't reject incoming
> policies with any of these set when in the raw/host policies they're
> clear.
>
> Signed-off-by: Jan Beulich <jbeulich@suse.com>

Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>

Like *everything* right now, there's no safety checking and rejection of
bad incoming policy data.  Xen will still zero out the bits it doesn't
like, and fixing this something which Roger and I are working on.  Its
basically the last piece of the "move to a new, better interface"
toolstack work.

~Andrew